Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 854 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.5739. Min Act: -0.0000

Data Index: 1105613 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.6303. Min Act: -0.0000

Data Index: 155770 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.7449. Min Act: -0.0000

Data Index: 3683 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.5875. Min Act: -0.0000

Data Index: 364358 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1279974 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.5666. Min Act: -0.0000

Data Index: 868735 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.5254. Min Act: -0.0000

Data Index: 740046 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.6203. Min Act: -0.0000

Data Index: 373935 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.3380. Min Act: -0.0000

Data Index: 1091230 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.4564. Min Act: -0.0000

Data Index: 1006635 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.3250. Min Act: -0.0000

Data Index: 92766 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.5639. Min Act: -0.0000

Data Index: 971635 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.2696. Min Act: -0.0000

Data Index: 1302177 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.2743. Min Act: -0.0000

Data Index: 620451 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.4384. Min Act: -0.0000

Data Index: 93560 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.3010. Min Act: -0.0000

Data Index: 996841 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.2802. Min Act: -0.0000

Data Index: 765501 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.2686. Min Act: -0.0000

Data Index: 578854 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.2337. Min Act: -0.0000

Data Index: 1166222 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 2.7449. Min Range: -2.7449

Max Act: 2.1144. Min Act: -0.0000

Data Index: 593266 (C4 (Web Text))

Max Activating Token Index: 956